强化学习论文趋势 2023–2026

主要结论

• 强化学习论文从 2023 年的 1,070 篇增长到 2026 年的 2,985 篇，三年间扩大到约 2.8 倍。
• NeurIPS 是发强化学习论文最多的会议，2023–2026 年共 2,494 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
• ICML 2026$\text{DT}^\text{2}$: Decision-Targeted Digital Twins
• ICLR 2026$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
• CVPR 2026A Causal Marriage between VLM and IRM from Understanding to
• NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
• ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
• ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
• CVPR 2025All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
• NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
• ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
• ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
• CVPR 2024DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
• NeurIPS 2023“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
• ICML 2023A Connection between One-Step RL and Critic Regularization in Reinforcement Learning
• ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
• CVPR 2023"Seeing" Electric Network Frequency From Events
• NeurIPS 2026$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
• ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
• ICLR 2026$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
• CVPR 2026AdaptVision Efficient Vision-Language Models via Adaptive Visual Acquisition

全部强化学习论文

共 379 篇，第 8 / 8 页

351. ICLR 2025Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations
352. ICLR 2025Towards Improving Exploration through Sibling Augmented GFlowNets
353. ICLR 2025TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
354. ICLR 2025Tractable Multi-Agent Reinforcement Learning through Behavioral Economics
355. ICLR 2025Training Language Models to Self-Correct via Reinforcement Learning
356. ICLR 2025Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking Correction
357. ICLR 2025Trajectory-Class-Aware Multi-Agent Reinforcement Learning
358. ICLR 2025Transformer-Squared: Self-adaptive LLMs
359. ICLR 2025Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning
360. ICLR 2025Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
361. ICLR 2025Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning
362. ICLR 2025Unhackable Temporal Reward for Scalable Video MLLMs
363. ICLR 2025UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP
364. ICLR 2025Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation
365. ICLR 2025UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement Learning
366. ICLR 2025Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization
367. ICLR 2025Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
368. ICLR 2025VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation
369. ICLR 2025VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
370. ICLR 2025VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning
371. ICLR 2025VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems
372. ICLR 2025WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
373. ICLR 2025What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
374. ICLR 2025What Makes a Good Diffusion Planner for Decision Making?
375. ICLR 2025WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
376. ICLR 2025XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
377. ICLR 2025Zero-shot Model-based Reinforcement Learning using Large Language Models
378. ICLR 2025Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
379. ICLR 2025Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

常见问题

2023–2026 年四大会议一共有多少篇强化学习论文？

共 6,885 篇，按年份分别是 2023 年 1,070 篇、2024 年 1,190 篇、2025 年 1,640 篇、2026 年 2,985 篇。

NeurIPS 2026 有多少篇强化学习论文？

NeurIPS 2026 有 760 篇强化学习论文，上一届是 784 篇。

ICLR 2026 有多少篇强化学习论文？

ICLR 2026 有 911 篇强化学习论文，上一届是 379 篇。

ICML 2026 有多少篇强化学习论文？

ICML 2026 有 1,021 篇强化学习论文，上一届是 405 篇。

CVPR 2026 有多少篇强化学习论文？

CVPR 2026 有 293 篇强化学习论文，上一届是 72 篇。

哪个会议的强化学习论文最多？

NeurIPS，2023–2026 年共 2,494 篇。